D-S evidential theory on sEMG signal recognition

  title={D-S evidential theory on sEMG signal recognition},
  author={Weiliang Ding and Gongfa Li and Ying Sun and Guozhang Jiang and Jianyi Kong and Honghai Liu},
  journal={Int. J. Comput. Sci. Math.},
In order to promote the accuracy and complexity in the recognition of sEMG signals by classifiers, this paper tells a method based on fused D-S evidential theory. Three features are discussed in the choice of parameters, which includes AR model coefficient, cepstral coefficients and time-domain integral absolute value. D-S evidential theory gets information based on information fusion of multi feature sets and multi classifiers. In recognition phase, many groups of data are used for the… 

Figures and Tables from this paper

Gesture Recognition Based on Kinect and sEMG Signal Fusion

The stimulation results show that comparing with other experimental methods, the decision fusion method based on weighted D-S evidence theory has higher utilization efficiency and recognition rate.

Surface EMG hand gesture recognition system based on PCA and GRNN

The principal component analysis method and GRNN neural network are used to construct the gesture recognition system, so as to reduce the redundant information of EMG signals, reduce the signal

Dynamic Gesture Recognition in the Internet of Things

The Kinect-based gesture recognition is analyzed in detail, and a dynamic gesture recognition method based on HMM and D-S evidence theory is proposed, which lays a good foundation for human–computer interaction under the IoTs technology.

Hand gesture recognition based on convolution neural network

The characteristics of convolution neural network are used to avoid the feature extraction process, reduce the number of parameters needs to be trained, and finally achieve the purpose of unsupervised learning.

Intelligent Human-Computer Interaction Based on Surface EMG Gesture Recognition

The recognition framework proposed in this paper can enhance the generalization ability of HCI in the long term use and it also simplifies the data collection stage before training the device ready for daily use, which is of great significance to improve the time generalization performance of an HCI system.

Decomposition algorithm for depth image of human health posture based on brain health

A hand posture decomposition algorithm is proposed that can remove redundant information and improve the robustness of the recognition algorithm and the accuracy of human body hand gesture description and the change of movement speed of robustness.

Hand Gesture Recognition Based on Surface Electromyogram Signal (sEMG) with Muscular Contraction Level and Real Time Implementation on An Artificial Prosthetic Wrist Using Artificial Neural Network (ANN)

It is found that the training and testing accuracy is better when both sEMG and flex signals are used for healthy person and another finding is that, for disable person, an artificial prosthetic wrist can replicate the hand gesture using s EMG signal but no significant change has been found using flex signal during the gesture recognition process.

Gesture recognition based on binocular vision

According to the cloud image information, it can be judged that the binocular vision system can effectively segment the gesture from the complex background.

Energy-efficient data collection and fusion in wireless body sensor networks for continuous health monitoring

Plusieurs defis existent dans les reseaux de capteurs corporels sans fil tels que la collecte et la fusion de donnees physiologiques dans un environnement contraignant. En effet, les nœuds de

Jointly network: a network based on CNN and RBM for gesture recognition

A jointly network of CNN and RBM is proposed for gesture recognition that mainly uses superposed network of multiple RBMs to carry out unsupervised feature extraction and combined with supervised feature extraction of CNN.



Uterine EMG analysis: a dynamic approach for change detection and classification

This algorithm of detection-classification-labeling gives satisfactory results on uterine EMG: in most cases more than 80% of the events are correctly detected and classified whatever the term of gestation.

A neural model for fuzzy Dempster-Shafer classifiers

Wavelet transform and real-time learning method for myoelectric signal in motion discrimination

The Wavelet transform using the Coiflet mother wavelet into the authors' real-time EMG prosthetic hand controller for discriminating motions from steady and unsteady EMG is introduced.

A study on group decision-making based fault multi-symptom-domain consensus diagnosis

An adaptive extreme learning machine algorithm and its application on face recognition

An adaptive extreme learning machine AP-ELM algorithm which automatically determines the number of hidden layer neurons based on the AP clustering algorithm is proposed which is used to face recognition.

EMG Pattern Analysis and Classification for a Prosthetic Arm

The results show very good separability of classes of movements when a learning pattern classification scheme is used, and a superposition principle seems to hold which may provide a means of decomposition of any composite motion to the six basic primitive motions.

Recognition of Facial Movements and Hand Gestures Using Surface Electromyogram(sEMG) for HCI Based Applications

  • S. ArjunanD. Kumar
  • Computer Science
    9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007)
  • 2007
Experimental results demonstrate that the features of sEMG recordings are suitable for characterising the muscle activation during unvoiced speech and subtle gestures, and the proposed system provides better results when is trained and tested by individual user.

The control of a prosthetic arm by EMG pattern recognition

An electromyographic signal pattern recognition system is constructed for real-time control of a prosthetic arm through precise identification of motion and speed command and a decomposition rule is formulated for the direct assignment of speed to each primitive motion involved in a combined motion.

Motor unit action potential number estimation in the surface electromyogram: wavelet matching method and its performance boundary

  • P. ZhouW. Rymer
  • Computer Science
    First International IEEE EMBS Conference on Neural Engineering, 2003. Conference Proceedings.
  • 2003
It is shown that the performance of wavelet matching methods is mainly determined by the MUAP superposition rate in the signal, and is compared to a highly selective multiple concentric ring surface electrode and a standard single differential surface EMG electrode.

Heating exchange process PIDNN control system research based on T-S fuzzy model

This paper adopts T-S fuzzy model to describe the input-output relationship based on collected data of heating exchange system and adopts PIDNN PID Neural Network controller to improve the control effect.